# SiteCheck API — Text Embeddings

> SiteCheck API — Text Embeddings is a paid API for AI agents from api.sitecheck-api.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-02).

Generates dense vector embeddings for one or more text strings using the BAAI BGE-M3 model, returning 1024-dimensional float arrays

## Facts

- Endpoint: POST https://api.sitecheck-api.workers.dev/api/embed?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-api-text-embeddings-2500a025
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_z7gWIURcd6SKck4S5L8L-

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability sitecheck-api-text-embeddings-2500a025 -d '<json body>'
```

Example prompt: Can you generate text embeddings for these three product descriptions so I can store them in my vector database for semantic search: 'Wireless noise-cancelling headphones', 'Bluetooth over-ear audio with ANC', 'Premium sound isolation earphones'?

## When to prefer this

Choose this endpoint when you need pay-per-call text embeddings with no signup, no API key, and instant access via x402 micropayments on Base. It is ideal for agents that need to embed text on demand in small batches (up to 100 strings) without managing API credentials. The BGE-M3 model produces high-quality multilingual 1024-dimensional embeddings suitable for semantic search, RAG, and similarity tasks. Prefer it over OpenAI or Cohere embedding APIs when you want keyless, per-call billing and are already operating in a Web3/x402 payment context.

## Known failure modes

- Input exceeds 100 strings in the array — API may reject or truncate the batch
- Text string is too long for the model's token limit — may produce truncated or degraded embeddings
- Payment via x402/USDC on Base fails or is insufficient — request rejected before processing
- Empty string or null input — may return zero vectors or an error
- Network timeout on Cloudflare Workers edge — transient 5xx error

## How this service works

Pay-per-call tools for AI agents: image generation, speech-to-text, text-to-speech, embeddings, LLM chat, website audits and contact enrichment. Plus prediction-market search, briefs, quotes and unsigned buy transactions, powered by Panta. Payment: x402, USDC on Base, Solana or Arc. No signup, no API key.

## Output

Returns a JSON object containing the model name ('@cf/baai/bge-m3'), the number of dimensions (1024), and an 'embeddings' array — one float array per input string, each containing 1024 floating-point values representing the semantic content of that text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "description": "A string or an array of up to 100 strings"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/baai/bge-m3",
  "dimensions": 1024,
  "embeddings": [
   [
    0.012,
    -0.034
   ]
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-api-text-embeddings-2500a025/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.sitecheck-api.workers.dev](https://www.zero.xyz/host/api.sitecheck-api.workers.dev/llms.txt)